News for hackers. Stuff that matters.
Re:OpenAI O3 breakthrough high score on ARC-AGI-PUB by internet_points on Saturday December 21, 2024 @03:49AM (#42478318)
> The fact that scaled reasoning models are finally showing progress on ARC proves that what it measures really is relevant and important for reasoning.

One might also interpret that as "the fact that models which are studying to the test are getting better at the test" (Goodhart's law), not that they're actually reasoning.

There are no comments on this comment yet.